電影資料的研究在近年大數據分析方法的成熟下，電影產業與學術界都有更進一步的頗析。產業界會參考賣座電影的成功因素，設法將成功因素應用於新電影製作上。然而，學術界也能透過觀眾評論的角度來看待賣座電影，而這個做法值得深究。

本研究以IMDb及其社群評論資料為分析對象，為製作公司歸納特定類型的賣座電影在情緒上的表現，提供觀眾評論對電影的成功關鍵情緒。主要研究問題：一、透過觀眾評論資料做「探索式分析」，圍繞在情緒上的趨勢特徵 二、「電影績效」如何隨評論情緒變化。研究結果顯示，以九大電影類型、國家、九大電影製作公司探索分析來看，確實有產出偏好情緒的電影類型。也發現特定電影類型要有好的票房表現，有其相對適配的正面情緒或極端情緒，最終提出類型、情緒對電影績效的影響。

With the advanced skills on data analysis applied on movie, movie industry and academia has gained further success. Movie industry will refer to the key factors of success movie, embarking them on new movie production. However, it is less common to see the aspect from audience toward blockbuster movie. Thus, this field is valuable to explore.

This study uses the data regarding IMDb and its review. It attempts to find out how will the sentiment perform on specific movie genres and provide some beneficail advice with the feeling from audience. The research focuses on sentiment features and implements into two parts－exploratory data analysis and movie performance. In our research, we explore the data from three perspectives, which are nine main genres, producing countries and nine major film studios. The conclusion showed that there are tendencies on sentiments of review within particular observations. As for the movie performance on sentiment, we also propose some movie genres may gain distinct performance from positive or extreme sentiment, which needs a suitable match. The research altimately presents the effect on performance from genres and sentiment.

論文審定書 i
誌謝 ii
中文摘要 iii
ABSTRACT iv
圖 次 vi
表 次 viii
第一章 緒論 1
第一節 研究背景與動機 1
第二節 研究目的 2
第三節 研究問題 2
第四節 研究架構 3
第二章 文獻探討 4
第一節 成功電影要素與預測 4
第二節 電影評論分析 6
第三節 電影類型的趨勢變化 8
第三章 研究方法 9
第一節 研究資料介紹與來源 9
第二節 資料前處理 10
第三節 探索式評論資料分析的資料準備 11
第四節 電影績效與評論分析的資料準備 13
第五節 研究流程與方法 14
第四章 研究結果 18
第一節 探索式評論資料分析 18
第二節 電影績效與評論分析 42
第五章 結論與建議 46
第一節 研究結論 46
第二節 研究限制與未來發展 47
參考文獻 48

Murschetz, P. C., Bruneel, C., Guy, J. L., Haughton, D., Lemercier, N., McLaughlin, M. D., ... & Bakhtawar, B. (2020). Movie Industry Economics: How Data Analytics Can Help Predict Movies’ Financial Success. Nordic Journal of Media Management, 1(3), 339-359.
Liu, A., Liu, Y., & Mazumdar, T. (2014). Star power in the eye of the beholder: A study of the influence of stars in the movie industry. Marketing Letters, 25(4), 385-396.
Lash, M. T & Zhao, K. (2016). Early predictions of movie success: The who, what, and when of profitability. Journal of Management Information Systems, 33(3), 874-903.
Chakraborty, P., Rahman, M. Z., & Rahman, S. (2006). Movie Success Prediction using Historical and Current Data Mining. International Journal of Computer Applications, 178(47), 1-5.
Bhave, A., Kulkarni, H., Biramane, V., & Kosamkar, P. (2015, January). Role of different factors in predicting movie success. In 2015 International Conference on Pervasive Computing (ICPC) Pune, pp. 1-4
Smit, E., & Pangarker, N. A. (2013). The determinants of box office performance in the film industry revisited. South African Journal of Business Management, 44(3), 47-58.
Hennig-Thurau, T., Houston, M. B., & Walsh, G. (2007). Determinants of motion picture box office and profitability: an interrelationship approach. Review of Managerial Science, 1(1), 65-92.
Mumtaz, D., & Ahuja, B. (2016, July). Sentiment analysis of movie review data using Senti-lexicon algorithm. In 2016 2nd International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT) (pp. 592-597). IEEE.
Lu, Y., Krüger, R., Thom, D., Wang, F., Koch, S., Ertl, T., & Maciejewski, R. (2014, October). Integrating predictive analytics and social media. In 2014 IEEE Conference on Visual Analytics Science and Technology (VAST) (pp. 193-202). IEEE.
Nagamma, P., Pruthvi, H. R., Nisha, K. K., & Shwetha, N. H. (2015, May). An improved sentiment analysis of online movie reviews based on clustering for box-office prediction. In International conference on computing, communication & automation (pp. 933-937). IEEE.
Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. arXiv preprint cs/0205070.
Redfern, N. (2012). Genre trends at the US box office, 1991 to 2010. European Journal of American Culture, 31(2), 145-167.
Miller, T., Govil, N., McMurria, J., Maxwell, R., & Wang, T. (2001). Global Hollywood, London: BFI. Miller Toby, Nitin Govil, John McMurria and Richard Maxwell.
Neale, S. (2000), Genre and Hollywood, London: Routledge.
Lu, W., Waterman, D., & Yan, M. Z. (2005). Changing markets, new technology, and violent content: An economic study of motion picture genre trends. Ann Arbor, 1001(48109), 734-7630500.
Song, M., & Chambers, T. (2014). Text mining with the Stanford CoreNLP. In Measuring scholarly impact (pp. 215-234). Springer, Cham.
Fast, E., Chen, B., & Bernstein, M. S. (2016, May). Empath: Understanding topic signals in large-scale text. In Proceedings of the 2016 CHI conference on human factors in computing systems (pp. 4647-4657).
Fokkema, M., & Zeileis, A. Fitting Generalized Linear Mixed-Effects Model Trees.
Ali, S. M., Nayak, G. K., Lenka, R. K., & Barik, R. K. (2018). Movie recommendation system using genome tags and content-based filtering. In Advances in Data and Information Sciences (pp. 85-94). Springer, Singapore.
Abdi, H., & Williams, L. J. (2010). Principal component analysis. Wiley interdisciplinary reviews: computational statistics, 2(4), 433-459.
Mishra, S. P., Sarkar, U., Taraphder, S., Datta, S., Swain, D., Saikhom, R., ... & Laishram, M. (2017). Multivariate statistical data analysis-principal component analysis (PCA). International Journal of Livestock Research, 7(5), 60-78.
Fokkema, M., Smits, N., Zeileis, A., Hothorn, T., & Kelderman, H. (2018). Detecting treatment-subgroup interactions in clustered data with generalized linear mixed-effects model trees. Behavior research methods, 50(5), 2016-2034.